EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Stability analysis for a recurrent sigma‒pi‒sigma neural network based on a batch gradient algorithm with L2 regularization

Liqing Zhang, Shibin Liang, Shikai Shen, Yujiao Wang, Fei Deng

PeerJ Computer Science · 03.07.2026 · 12 · e3956

DOI: 10.7717/peerj-cs.3956 ↗

Kurz gefasst

Fachartikel in der Zeitschrift PeerJ Computer Science, online erschienen am 03.07.2026. Verfasst von Liqing Zhang und 4 weiteren Autor:innen. Die Arbeit nennt 40 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Yunnan Provincial Undergraduate Universities Association, Yunan Students’ innovation and Entrepreneurship Training Program, Yunnan Provincial Department of Education.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Higher-order neural networks (HONNs) have more powerful nonlinear mapping capabilities than traditional feed-forward neural networks do. The recurrent sigma-pi-sigma neural network (RSPSNN), a multilayer higher-order neural network, suffers from slow convergence and poor generalizability when trained using a traditional gradient learning algorithm. To overcome these drawbacks, this work presents a method of accelerating the training of the RSPSNN on the basis of L2 regularization, and the results show that the L2 regularity term can effectively accelerate the convergence of the network during the training process. In addition, we rigorously demonstrate the convergence stability of the proposed algorithm, and the performance of the algorithm is evaluated via classification and approximation experiments, which confirm the theoretical results of this article.

Förderung

  • Yunnan Provincial Undergraduate Universities Association
  • Yunan Students’ innovation and Entrepreneurship Training Program
  • Yunnan Provincial Department of Education

Zitieren

APA

Zhang, L., Liang, S., Shen, S., Wang, Y., & Deng, F. (2026). Stability analysis for a recurrent sigma‒pi‒sigma neural network based on a batch gradient algorithm with L2 regularization. PeerJ Computer Science, 12, e3956. https://doi.org/10.7717/peerj-cs.3956

Vancouver

Zhang L, Liang S, Shen S, Wang Y, Deng F. Stability analysis for a recurrent sigma‒pi‒sigma neural network based on a batch gradient algorithm with L2 regularization. PeerJ Computer Science. 2026;12:e3956. doi:10.7717/peerj-cs.3956

BibTeX
@article{Zhang2026,
  author = {Zhang, Liqing and Liang, Shibin and Shen, Shikai and Wang, Yujiao and Deng, Fei},
  title = {Stability analysis for a recurrent sigma‒pi‒sigma neural network based on a batch gradient algorithm with L2 regularization},
  journal = {PeerJ Computer Science},
  year = {2026},
  volume = {12},
  pages = {e3956},
  doi = {10.7717/peerj-cs.3956}
}
Kostenlos starten →